I am the Magerman Term Assistant Professor of Computer and Information Science at the University of Pennsylvania. I am affiliated with the Theory group, the ASSET Center on safe, explainable, and trustworthy AI systems, and the Warren Center for network and data sciences.
I work on a range of problems at the intersection of theoretical computer science and machine learning, driven by the goal of making modern AI systems trustworthy. My work contributes to understanding how models reason internally and why they fail, building learning algorithms that come with provable safety guarantees, and designing interaction protocols that allow humans and AI to collaborate reliably even when misaligned.
My research has been recognized by an Alfred P. Sloan Research Fellowship (2026), a Schmidt Sciences AI2050 Early Career Fellowship (2025), an NSF CAREER award (2026), and an Amazon Research Award (2025). My group also receives support from NSF and has received support from the UK's AI Security Institute (AISI), Microsoft Research, and OpenAI.
Before joining Penn, I was a postdoc at Microsoft Research NYC. I obtained my Ph.D. from the University of Texas at Austin, where I was fortunate to be advised by Adam Klivans. My PhD research was supported by a JP Morgan AI PhD Fellowship and a Simons-Berkeley Research Fellowship, and my thesis titled 'Towards Provably Efficient Algorithms for Learning Neural Networks' received the Bert Kay Dissertation Award.